WO2018228422A1 - 一种发出预警信息的方法、装置及系统 - Google Patents

一种发出预警信息的方法、装置及系统 Download PDF

Info

Publication number
WO2018228422A1
WO2018228422A1 PCT/CN2018/091028 CN2018091028W WO2018228422A1 WO 2018228422 A1 WO2018228422 A1 WO 2018228422A1 CN 2018091028 W CN2018091028 W CN 2018091028W WO 2018228422 A1 WO2018228422 A1 WO 2018228422A1
Authority
WO
WIPO (PCT)
Prior art keywords
warning information
similarity
early warning
threshold
preset
Prior art date
Application number
PCT/CN2018/091028
Other languages
English (en)
French (fr)
Inventor
王俊松
Original Assignee
杭州海康威视数字技术股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州海康威视数字技术股份有限公司 filed Critical 杭州海康威视数字技术股份有限公司
Priority to US16/622,864 priority Critical patent/US11361586B2/en
Priority to EP18817320.7A priority patent/EP3640838A4/en
Publication of WO2018228422A1 publication Critical patent/WO2018228422A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions

Definitions

  • the present disclosure relates to the field of electronic technology, and more particularly to a method, apparatus, and system for issuing early warning information.
  • the face image captured by the shooting device of each traffic location (such as a subway station, an airport, etc.) is generally compared with the face image of the target person stored in advance to determine the target person's location. position.
  • the photographing device of each traffic position may have the function of capturing a face image
  • the terminal may continuously acquire the face image captured by the photographing device, and further, the person photographed by the photographing device may be calculated according to a preset face recognition algorithm.
  • the similarity between the face image and the face image of the target person stored in advance, if the similarity is greater than the preset similarity threshold, the warning information is sent (for example, the face image captured by the camera and the calculated similarity may be displayed) ). After the staff sees the warning information, it can be confirmed again whether the face image captured by the camera is the target person, and if so, it can be determined that the target person appears at the position where the camera is located.
  • the face image captured by the camera may not be clear (such as a scene where the face image is not clear due to foggy days).
  • the calculated similarity and the preset similarity threshold are calculated. If the comparison is made, it may lead to misjudgment (that is, when the captured face image is a non-target person, it may be mistakenly judged as the target person), and the warning information issued may contain a large number of warning information caused by misjudgment, thereby The accuracy of the warning is low.
  • the present disclosure provides a method, device and system for issuing early warning information.
  • the technical solution is as follows:
  • a method of issuing early warning information comprising:
  • the target similarity reaches the calculated similarity threshold corresponding to the current scene, the early warning information corresponding to the first facial image is sent.
  • the determining, according to the volatility degree value of the similarity corresponding to the generated early warning information, determining a similarity threshold corresponding to the current scenario including:
  • the average value of the similarity corresponding to the generated early warning information is determined as the similarity threshold corresponding to the current scene.
  • the method further includes:
  • the volatility degree value is less than the second preset volatility threshold, and the number of the generated early warning information is less than the first preset number threshold, determining the down-regulated value and lowering the last determined similarity threshold The difference of the values is determined as the similarity threshold corresponding to the current scene.
  • the method further includes:
  • the last determined similarity threshold is determined as the similarity threshold corresponding to the current scenario.
  • the obtaining the similarity corresponding to the generated early warning information includes:
  • the obtaining the similarity corresponding to the generated early warning information includes:
  • the similarity corresponding to the generated early warning information is acquired.
  • the method further includes:
  • determining the target early warning information to be deleted including:
  • the warning information of the corresponding generation time from the current time is greater than the preset time threshold, and is determined as the target warning information to be deleted;
  • the preset number of pieces of early warning information that the generation time is the largest from the current time is determined as the target warning information to be deleted.
  • an apparatus for issuing early warning information comprising:
  • An obtaining module configured to acquire a similarity corresponding to the generated warning information
  • a determining module configured to determine a similarity threshold corresponding to the current scenario according to the volatility degree value of the similarity corresponding to the generated early warning information
  • a calculation module configured to calculate a target similarity between the first face image and a pre-stored target face image according to a preset face recognition algorithm each time a first face image captured by the camera device is acquired ;
  • a sending module configured to send the early warning information corresponding to the first face image if the target similarity reaches the calculated similarity threshold corresponding to the current scene.
  • the determining module is configured to:
  • the average value of the similarity corresponding to the generated early warning information is determined as the similarity threshold corresponding to the current scene.
  • the determining module is further configured to:
  • the volatility degree value is less than the second preset volatility threshold, and the number of the generated early warning information is less than the first preset number threshold, determining the down-regulated value and lowering the last determined similarity threshold The difference of the values is determined as the similarity threshold corresponding to the current scene.
  • the determining module is further configured to:
  • the last determined similarity threshold is determined as the similarity threshold corresponding to the current scenario.
  • the obtaining module is configured to:
  • the obtaining module is configured to:
  • the similarity corresponding to the generated early warning information is acquired.
  • the determining module is further configured to:
  • the determining module is configured to:
  • the warning information of the corresponding generation time from the current time is greater than the preset time threshold, and is determined as the target warning information to be deleted;
  • the preset number of pieces of early warning information that the generation time is the largest from the current time is determined as the target warning information to be deleted.
  • a computer readable storage medium having stored therein a computer program, the computer program being executed by a processor to implement the method steps of the first aspect.
  • a system for issuing early warning information comprising: the apparatus of the second aspect, and a photographing apparatus.
  • a terminal where the terminal includes:
  • One or more processors are One or more processors.
  • the memory stores one or more programs, the one or more programs configured to be executed by the one or more processors, the one or more programs comprising performing the method as described in the first aspect Instructions for method steps.
  • the terminal may obtain the similarity corresponding to the early warning information that has been generated by the history, and determine the similarity threshold corresponding to the current scene according to the volatility degree value of the similarity corresponding to the early warning information, and further, when calculating the shooting device
  • the target similarity may be compared with the similarity threshold corresponding to the determined current scene, if the target similarity reaches the similarity threshold corresponding to the current scene.
  • the warning information corresponding to the first face image is issued, wherein when the captured face image is not clear, the degree of volatility of the similarity between the captured face image and the target face image is often calculated.
  • the similarity threshold can be obtained by increasing the similarity threshold to match the current scene.
  • each time the terminal obtains the target similarity it compares the similarity thresholds that are adapted to the current scene, and does not compare with the preset similarity threshold, thereby reducing the number of early warning information sent by misjudgment.
  • the accuracy of the warning can be improved.
  • FIG. 1 is a flowchart of a method for issuing early warning information according to an exemplary embodiment
  • FIG. 2 is a schematic diagram of a system frame according to an exemplary embodiment
  • FIG. 3 is a schematic diagram of an apparatus for issuing early warning information according to an exemplary embodiment
  • FIG. 4 is a schematic structural diagram of a terminal according to an exemplary embodiment
  • FIG. 5 is a schematic diagram of a system for issuing early warning information, according to an exemplary embodiment.
  • An exemplary embodiment of the present disclosure provides a method of issuing early warning information, which may be used in a terminal, wherein the terminal may be a personal computer, and the terminal may perform data communication with a front end device (photographing device).
  • the terminal may be provided with a processor, a memory and a transceiver.
  • the processor may be used to obtain related processing of the warning information, and the memory may be used to store data required and generated in the following processing, and the transceiver may be used for receiving and transmitting. data.
  • a display can also be provided, which can be used to display warning information.
  • step 101 the similarity corresponding to the generated early warning information is obtained.
  • the terminal may have a face alert function and may have an initial similarity threshold stored in advance.
  • the terminal can acquire the face image captured by the photographing device with which the data communication is performed in real time.
  • the terminal may calculate the similarity between the face image and the target face image of the target person stored in advance according to a preset face recognition algorithm, and further, the similarity and the obtained degree may be determined.
  • the magnitude relationship of the initial similarity threshold if the calculated similarity is greater than or equal to the initial similarity threshold, the terminal may generate and send the early warning information corresponding to the facial image, where the warning information corresponding to the facial image may include a human face
  • the image, the similarity, and the target face image may further include a location where the photographing device that photographs the face image is located. That is to say, in the initial stage, each time the similarity is calculated, it can be compared with the initial similarity threshold.
  • the target face image may be a server or a terminal or a face image stored in the photographing device, for example, a face photo of a child of the registered user, a photo of the lost old man, and the like.
  • the terminal can adaptively adjust the similarity threshold corresponding to the current scene according to the scene change. Specifically, a calculation trigger event with a similarity threshold may be set in the terminal. When the face warning function is enabled, when the calculation trigger event of the similarity threshold is detected, the similarity of the generated early warning information may be obtained. degree.
  • the calculation trigger event based on the similarity threshold is different, and the processing manner of step 101 can be various.
  • processing methods are given below:
  • an acquisition period may be preset in the terminal, that is, a preset acquisition period may be used as a calculation trigger event of the similarity threshold. That is to say, in the state in which the face warning function is enabled, the terminal can obtain the similarity corresponding to the generated early warning information in the previous acquisition period after each preset acquisition period. For example, when the terminal receives the face warning function opening command at 9:00 and the period is one hour, the terminal can obtain the similarity of the warning information generated between 9:00 and 10:00 when the time reaches 10:00. When the time reaches 11:00, the terminal can obtain the similarity corresponding to the warning information generated between 10:00 and 11:00, and so on.
  • a quantity threshold (ie, a second preset number threshold) may be pre-stored in the terminal.
  • the terminal may obtain the similarity corresponding to the generated early warning information, when the number of the generated early warning information reaches the second preset number threshold.
  • the terminal can obtain the similarity of the generated 20 early warning information when the number of the generated early warning information reaches 20, the terminal can obtain the similarity of the generated 20 early warning information.
  • the number of generated early warning information can be re-counted. When the number of the generated early warning information reaches 20 again, the terminal can obtain the similarity corresponding to the 20 generated early warning information.
  • each time the similarity threshold is calculated the timing can be restarted, and the number of generated early warning information is restarted, wherein the specific processing for calculating the similarity threshold will be performed subsequently.
  • the timing duration reaches the preset duration, or the number of counts reaches the second preset number threshold, the similarity corresponding to the generated warning information is obtained, that is, the terminal can obtain the generated one as long as one of the above conditions is satisfied. The similarity of the warning information.
  • step 102 the similarity threshold corresponding to the current scene is determined according to the volatility degree value of the similarity corresponding to the generated early warning information.
  • the terminal may determine the volatility degree value of the similarity corresponding to the generated early warning information, and further, may be based on the determined volatility degree value.
  • the size of the similarity threshold is adjusted, and the adjusted similarity threshold is determined as the similarity threshold corresponding to the current scene.
  • the specific processing process for determining the similarity threshold may be as follows: calculating a volatility degree value of the similarity corresponding to the generated early warning information; and if the volatility degree value is greater than the first preset volatility threshold, the generated early warning is generated.
  • the average value of the similarity corresponding to the information is determined as the similarity threshold corresponding to the current scene.
  • the terminal may calculate a volatility degree value of the similarity according to a preset calculation formula of the volatility degree value, wherein the volatility degree value It may be the variance or standard deviation of the similarity corresponding to the generated warning information. For example, if the similarity of the four generated early warning information is a, b, c, and d, the terminal can calculate the variance or standard deviation of a, b, c, and d according to the formula of variance or standard deviation. . After obtaining the volatility degree value, the terminal may compare it with the first preset volatility threshold, if the volatility degree value of the acquired similarity is greater than the first preset volatility threshold (in this case, the current scene is captured.
  • the terminal may calculate the average value of the similarity corresponding to the generated warning information, and further The calculated average value can be determined as the similarity threshold corresponding to the current scene.
  • the similarity threshold corresponding to the current scenario may be appropriately increased, so that the number of early warning information generated by the terminal is reduced, and thus, the work can be alleviated. The pressure on personnel to manually confirm early warning information.
  • the previous similarity threshold is 70
  • the similarity of the obtained early warning information is 71, 75, 80, and 78 respectively
  • the terminal can determine the average value 76 of 71, 75, 80, and 78 as the current scene.
  • Corresponding similarity threshold is 70
  • the terminal may further reduce the similarity threshold of the subsequent use when the similarity threshold is high.
  • the processing may be as follows: if the volatility degree value is smaller than the second preset volatility threshold, and the generated If the number of the early warning information is less than the first preset number threshold, the down value is determined, and the difference between the previously determined similarity threshold and the downgrade value is determined as the similarity threshold corresponding to the current scene.
  • the terminal may further compare the volatility degree value with the second preset volatility threshold. If the volatility degree value is less than the second preset volatility threshold, the terminal may further Comparing the obtained number of generated early warning information with the size of the first preset number threshold, if the number of generated early warning information is less than the first preset number threshold, the terminal may be appropriate based on the original similarity threshold Reduce the similarity threshold.
  • the terminal may determine the last time the downgrade value is determined.
  • the difference between the similarity threshold and the down-regulated value is determined as the similarity threshold corresponding to the current scene, wherein the down-value may be a preset value or may be determined according to the previously determined similarity threshold.
  • the terminal may determine the half of the difference between the upper limit value of the similarity and the previously determined similarity threshold as a downward value.
  • the last determined similarity threshold is 80, and the upper limit is 100, the terminal can determine half of the difference between 100 and 80 (ie, 10) as the down-regulated value.
  • the similarity threshold can be appropriately lowered, so that the terminal can generate an appropriate amount of early warning information and increase the possibility of finding the target person.
  • the terminal may not change the similarity threshold that is determined when the similarity threshold is within the preset range.
  • the process may be as follows: if the volatility degree value is less than or equal to the first preset The fluctuation threshold is greater than or equal to the second preset fluctuation threshold, and the last determined similarity threshold is determined as the similarity threshold corresponding to the current scene.
  • the terminal may obtain the similarity threshold that is determined last time, and may determine the similarity threshold corresponding to the current scenario. In this case, the last similarity threshold may not be performed. Changes can be continued in the subsequent process.
  • step 103 each time the first face image captured by the photographing device is acquired, the target similarity between the first face image and the pre-stored target face image is calculated according to the preset face recognition algorithm.
  • the terminal can perform data communication with the front end device (photographing device), and each time the camera captures a face image (which may be referred to as a first face image), it can transmit it to the terminal, such as Figure 2 shows.
  • the terminal may calculate a similarity (ie, target similarity) between the first face image and the pre-stored target face image according to a preset face recognition algorithm, where the target face image It can be the face image of the target person.
  • a similarity ie, target similarity
  • the terminal may send the similarity threshold to the photographing device. Accordingly, after the photographing device receives the similarity threshold corresponding to the current scene, the terminal may store the image, and each time the image is captured.
  • the first face image and the received similarity threshold may be generated according to a preset format.
  • the task data including the first face map and the similarity threshold may be generated in the form of a table, and the task data may further include information such as a location and an identifier of the photographing device.
  • the task data may be sent to the terminal.
  • the terminal may acquire the first face image and calculate the target of the first face image and the pre-stored target face image. Similarity.
  • step 104 if the target similarity reaches the determined similarity threshold corresponding to the current scene, the early warning information corresponding to the first facial image is sent.
  • the terminal compares the target similarity with the determined similarity threshold of the current scenario, if the target similarity reaches the determined similarity of the current scenario.
  • the threshold value is used, the terminal may generate and send the warning information corresponding to the first face image, where the terminal may display the early warning information corresponding to the first face image, or the terminal displays the early warning information corresponding to the first face image, An alarm sounds.
  • the terminal When the terminal communicates with the photographing devices of the plurality of locations, that is, when the terminal can acquire the face images captured by the photographing devices of the plurality of locations, the terminal may respectively determine the similarity threshold of the subsequent use corresponding to each location, that is, Each location, the terminal can be processed according to the method described in the above steps 101-104.
  • the similarity degree of the generated early warning information is obtained; and the similarity threshold corresponding to the current scene of the location is determined according to the volatility degree value of the similarity corresponding to the generated early warning information;
  • the target similarity between the first face image and the pre-stored target face image is calculated according to the preset face recognition algorithm; if the target similarity reaches the target
  • the similarity threshold corresponding to the current scene of the location sends the warning information corresponding to the first facial image.
  • the terminal may also delete the generated early warning information.
  • the processing may be as follows: when detecting the occurrence of the warning information deletion triggering event, determining the target early warning information to be deleted; and determining the target early warning information. delete.
  • the terminal may further preset a deletion mechanism for the generated early warning information.
  • the terminal may be configured with an alarm information deletion trigger event in advance, and each time the detection of the warning information deletion trigger event occurs, the terminal may determine the warning information to be deleted in the currently stored warning information (may be referred to as a target Warning information). After the target warning information is determined, the terminal may delete the terminal from the terminal, so that the terminal may have sufficient storage space to store the generated early warning information.
  • the manner of determining the target early warning information may be various, and several feasible processing methods are given below:
  • the warning information of the corresponding generation time from the current time is greater than the preset time threshold, and is determined as the target warning information to be deleted.
  • each time the terminal generates the early warning information may record the generation time corresponding to each of the early warning information.
  • the terminal may be configured with a deletion time in advance, and when the current time is detected as the preset deletion time, the terminal may determine, in all the currently stored warning information, the duration of the generation time corresponding to each warning information from the current time.
  • each time length obtained may be compared with a preset duration threshold, and the warning information of the corresponding generation time from the current time is greater than the preset duration threshold, and is determined as the target warning information to be deleted.
  • the preset number of pieces of early warning information with the largest generation time from the current time is determined as the target warning information to be deleted.
  • each time the terminal generates the early warning information may record the generation time corresponding to each of the early warning information.
  • the terminal may be configured with a deletion time in advance, and when the current time is detected as the preset deletion time, the terminal may determine, in all the currently stored warning information, the duration of the generation time corresponding to each warning information from the current time. Further, each of the early warning information may be sorted in descending order of the corresponding duration. After the sorted warning information is obtained, a preset number of early warning information may be selected from front to back, and then the selected preset number of early warning information may be determined as the target early warning information to be deleted.
  • the terminal may obtain the similarity corresponding to the early warning information that has been generated by the history, and determine the similarity threshold corresponding to the current scene according to the volatility degree value of the similarity corresponding to the early warning information, and further, when calculating the shooting device
  • the target similarity may be compared with the similarity threshold corresponding to the determined current scene, if the target similarity reaches the similarity threshold corresponding to the current scene.
  • the warning information corresponding to the first face image is issued.
  • the degree of volatility of the similarity between the captured face image and the target face image is often calculated.
  • the similarity threshold can be improved to obtain The similarity threshold for the current scene.
  • each time the terminal obtains the target similarity it compares the similarity thresholds that are adapted to the current scene, and does not compare with the preset similarity threshold, thereby reducing the number of early warning information sent by misjudgment.
  • the accuracy of the warning can be improved.
  • Yet another exemplary embodiment of the present disclosure provides an apparatus for issuing early warning information. As shown in FIG. 3, the apparatus includes:
  • the obtaining module 310 is configured to acquire a similarity corresponding to the generated early warning information.
  • the determining module 320 is configured to determine a similarity threshold corresponding to the current scene according to the volatility degree value of the similarity corresponding to the generated early warning information;
  • the calculating module 330 is configured to calculate, according to the preset face recognition algorithm, the first face image is similar to the target of the pre-stored target face image, when the first face image captured by the photographing device is acquired. degree;
  • the issuing module 340 is configured to send the early warning information corresponding to the first face image if the target similarity reaches the determined similarity threshold corresponding to the current scene.
  • the determining module 320 is configured to:
  • the average value of the similarity corresponding to the generated early warning information is determined as the similarity threshold corresponding to the current scene.
  • the determining module 320 is further configured to:
  • the volatility degree value is less than the second preset volatility threshold, and the number of the generated early warning information is less than the first preset number threshold, determining the down-regulated value and lowering the last determined similarity threshold The difference of the values is determined as the similarity threshold corresponding to the current scene.
  • the determining module 320 is further configured to:
  • the last determined similarity threshold is determined as the similarity threshold corresponding to the current scenario.
  • the obtaining module 310 is configured to:
  • the obtaining module 310 is configured to:
  • the similarity corresponding to the generated early warning information is acquired.
  • the determining module 320 is further configured to:
  • the determining module 320 is configured to:
  • the warning information of the corresponding generation time from the current time is greater than the preset time threshold, and is determined as the target warning information to be deleted;
  • the preset number of pieces of early warning information that the generation time is the largest from the current time is determined as the target warning information to be deleted.
  • the terminal may obtain the similarity corresponding to the early warning information that has been generated by the history, and determine the similarity threshold corresponding to the current scene according to the volatility degree value of the similarity corresponding to the early warning information, and further, when calculating the shooting device
  • the target similarity may be compared with the similarity threshold corresponding to the determined current scene, if the target similarity reaches the similarity threshold corresponding to the current scene.
  • the warning information corresponding to the first face image is issued, wherein when the captured face image is not clear, the degree of volatility of the similarity between the captured face image and the target face image is often calculated.
  • the similarity threshold can be obtained by increasing the similarity threshold to match the current scene.
  • each time the terminal obtains the target similarity it compares the similarity thresholds that are adapted to the current scene, and does not compare with the preset similarity threshold, thereby reducing the number of early warning information sent by misjudgment.
  • the accuracy of the warning can be improved.
  • the device for sending the early warning information is only illustrated by the division of the above functional modules.
  • the functions may be allocated by different functional modules according to requirements. Completion, that is, the internal structure of the terminal is divided into different functional modules to complete all or part of the functions described above.
  • the device for issuing the early warning information provided by the foregoing embodiment is the same as the method for transmitting the early warning information. For the specific implementation process, refer to the method embodiment, and details are not described herein again.
  • terminal 400 can include one or more of the following components: processing component 402, memory 404, power component 406, multimedia component 408, audio component 410, input/output (I/O) interface 412, sensor component 414, And a communication component 416.
  • Processing component 402 typically controls the overall operations of terminal 400, such as operations associated with display, data communication, camera operations, and recording operations.
  • Processing component 402 can include one or more processors 420 to execute instructions to perform all or part of the steps of the above described methods.
  • processing component 402 can include one or more modules to facilitate interaction between component 402 and other components.
  • processing component 402 can include a multimedia module to facilitate interaction between multimedia component 408 and processing component 402.
  • Memory 404 is configured to store various types of data to support operation at terminal 400. Examples of such data include instructions for any application or method operating on terminal 400, contact data, phone book data, messages, pictures, videos, and the like. Memory 404 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable. Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Disk Disk or Optical Disk.
  • Power component 406 provides power to various components of terminal 400.
  • Power component 406 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for audio output device 400.
  • the multimedia component 408 includes a screen between the terminal 400 and the user that provides an output interface.
  • the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
  • the multimedia component 408 includes a front camera and/or a rear camera. When the terminal 400 is in an operation mode such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 410 is configured to output and/or input an audio signal.
  • the audio component 410 includes a microphone (MIC) that is configured to receive an external audio signal when the audio output device 400 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 404 or transmitted via communication component 416.
  • the I/O interface 412 provides an interface between the processing component 402 and the peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.
  • Sensor assembly 414 includes one or more sensors for providing terminal 400 with various aspects of status assessment.
  • sensor component 414 can detect an open/closed state of terminal 400, a relative positioning of components, such as the display and keypad of terminal 400, and sensor component 414 can also detect a change in position of a component of terminal 400 or terminal 400. The presence or absence of contact of the user with the terminal 400, the orientation or acceleration/deceleration of the terminal 400, and the temperature change of the terminal 400.
  • Sensor assembly 414 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • Sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 414 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 416 is configured to facilitate wired or wireless communication between terminal 400 and other devices.
  • the terminal 400 can access a wireless network based on a communication standard such as WiFi, 2G or 3G, or a combination thereof.
  • communication component 416 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • the communication component 416 also includes a near field communication (NFC) module to facilitate short range communication.
  • NFC near field communication
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • terminal 400 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable A gate array
  • controller microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • non-transitory computer readable storage medium comprising instructions, such as a memory 404 comprising instructions executable by the processor 420 of the terminal 400 to perform the above method.
  • the non-transitory computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • a non-transitory computer readable storage medium the instructions in the storage medium being executed by a processor to implement a method for issuing early warning information, the method comprising:
  • the target similarity reaches the determined similarity threshold corresponding to the current scene, the early warning information corresponding to the first facial image is sent.
  • the instructions in the storage medium are also executable by the processor to implement:
  • the average value of the similarity corresponding to the generated early warning information is determined as the similarity threshold corresponding to the current scene.
  • the instructions in the storage medium are also executable by the processor to implement:
  • the volatility degree value is less than the second preset volatility threshold, and the number of the generated early warning information is less than the first preset number threshold, determining the down-regulated value and lowering the last determined similarity threshold The difference of the values is determined as the similarity threshold corresponding to the current scene.
  • the instructions in the storage medium are also executable by the processor to implement:
  • the last determined similarity threshold is determined as the similarity threshold corresponding to the current scenario.
  • the instructions in the storage medium are also executable by the processor to implement:
  • the instructions in the storage medium are also executable by the processor to implement:
  • the similarity corresponding to the generated early warning information is acquired.
  • the instructions in the storage medium are also executable by the processor to implement:
  • the instructions in the storage medium are also executable by the processor to implement:
  • the warning information of the corresponding generation time from the current time is greater than the preset time threshold, and is determined as the target warning information to be deleted;
  • the preset number of pieces of early warning information that the generation time is the largest from the current time is determined as the target warning information to be deleted.
  • the present disclosure provides a system 500 for issuing early warning information, including: an apparatus 501 for issuing early warning information provided by the above embodiment, and a photographing apparatus 502.
  • the terminal may obtain the similarity corresponding to the early warning information that has been generated by the history, and determine the similarity threshold corresponding to the current scene according to the volatility degree value of the similarity corresponding to the early warning information, and further, when calculating the shooting device
  • the target similarity may be compared with the similarity threshold corresponding to the determined current scene, if the target similarity reaches the similarity threshold corresponding to the current scene.
  • the warning information corresponding to the first face image is issued, wherein when the captured face image is not clear, the degree of volatility of the similarity between the captured face image and the target face image is often calculated.
  • the similarity threshold can be obtained by increasing the similarity threshold to match the current scene.
  • each time the terminal obtains the target similarity it compares the similarity thresholds that are adapted to the current scene, and does not compare with the preset similarity threshold, thereby reducing the number of early warning information sent by misjudgment.
  • the accuracy of the warning can be improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)

Abstract

本公开是关于一种发出预警信息的方法、装置及系统，属于电子技术领域。所述方法包括：获取已生成的预警信息对应的相似度；根据所述已生成的预警信息对应的相似度的波动性程度值，计算当前场景对应的相似度阈值；每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；如果所述目标相似度达到计算出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。采用本公开，可以提高预警的精确度。

Description

一种发出预警信息的方法、装置及系统
本申请要求于2017年6月15日提交中国国家知识产权局、申请号为201710454708.8、发明名称为“一种发出预警信息的方法、装置及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开是关于电子技术领域，尤其是关于一种发出预警信息的方法、装置及系统。
背景技术
为抓取某目标人物，一般会通过将各个交通位置(比如地铁站、机场等)的拍摄装置拍摄的人脸图像与预先存储的目标人物的人脸图像进行比对，来确定目标人物所在的位置。
具体的，各个交通位置的拍摄装置可以具有抓拍人脸图像的功能，终端可以不断获取拍摄装置拍摄到的人脸图像，进而，可以根据预设的人脸识别算法，计算拍摄装置拍摄到的人脸图像与预先存储的目标人物的人脸图像的相似度，如果相似度大于预设的相似度阈值，则发出预警信息(比如，可以显示拍摄装置拍摄到的人脸图像和计算出的相似度)。工作人员看到预警信息后，可以再次确认拍摄装置拍摄到的人脸图像是否是目标人物，如果是，则可以确定目标人物出现在拍摄装置所在的位置。
在实现本公开的过程中，发明人发现上述技术至少存在以下问题：
某些场景下拍摄装置拍摄到的人脸图像可能不清晰(比如雾天导致拍摄的人脸图像不清晰的场景)，此种场景下，再将计算出的相似度与预设的相似度阈值进行比较的话，可能会导致误判(即拍摄到的人脸图像是非目标人物时，可能将其误判为目标人物)，进而，导致发出的预警信息包含大量的误判引发的预警信息，从而，导致预警的精确度较低。
发明内容
为了克服相关技术中存在的预警的精确度较低的问题，本公开提供了一种发出预警信息的方法、装置及系统。所述技术方案如下：
根据本公开实施例的第一方面，提供一种发出预警信息的方法，所述方法包括：
获取已生成的预警信息对应的相似度；
根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值；
每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；
如果所述目标相似度达到计算出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。
可选的，所述根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值，包括：
计算所述已生成的预警信息对应的相似度的波动性程度值；
如果所述波动性程度值大于第一预设波动阈值，则将所述已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
可选的，所述方法还包括：
如果所述波动性程度值小于第二预设波动阈值，且所述已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
可选的，所述方法还包括：
如果所述波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的相似度阈值，确定为当前场景对应的相似度阈值。
可选的，所述获取已生成的预警信息对应的相似度，包括：
每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
可选的，所述获取已生成的预警信息对应的相似度，包括：
每当已生成的预警信息的数量达到第二预设数量阈值时，获取所述已生成的预警信息对应的相似度。
可选的，所述方法还包括：
当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；
将确定出的所述目标预警信息删除。
可选的，所述当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息，包括：
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息；或者，
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
根据本公开实施例的第二方面，提供一种发出预警信息的装置，所述装置包括：
获取模块，用于获取已生成的预警信息对应的相似度；
确定模块，用于根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值；
计算模块，用于每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；
发出模块，用于如果所述目标相似度达到计算出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。
可选的，所述确定模块，用于：
计算所述已生成的预警信息对应的相似度的波动性程度值；
如果所述波动性程度值大于第一预设波动阈值，则将所述已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
可选的，所述确定模块，还用于：
如果所述波动性程度值小于第二预设波动阈值，且所述已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
可选的，所述确定模块，还用于：
如果所述波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的相似度阈值，确定为当前场景对应的相似度阈值。
可选的，所述获取模块，用于：
每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
可选的，所述获取模块，用于：
每当已生成的预警信息的数量达到第二预设数量阈值时，获取所述已生成的预警信息对应的相似度。
可选的，所述确定模块，还用于：
当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；
将确定出的所述目标预警信息删除。
可选的，所述确定模块，用于：
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息；或者，
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
根据本公开实施例的第三方面，提供一种计算机可读存储介质，所述存储介质内存储有计算机程序，所述计算机程序被处理器执行时实现第一方面的方法步骤。
根据本公开实施例的第四方面，提供一种发出预警信息的系统，所述系统包括：如第二方面所述的装置，以及拍摄装置。
根据本公开实施例的第五方面，提供一种终端，所述终端包括：
一个或多个处理器；和
存储器；
所述存储器存储有一个或多个程序，所述一个或多个程序被配置成由所述一个或多个处理器执行，所述一个或多个程序包含用于进行如第一方面所述的方法步骤的指令。
本公开的实施例提供的技术方案可以包括以下有益效果：
本公开实施例中，终端可以获取历史已经生成的预警信息对应的相似度，并根据预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值，进而，当计算出拍摄装置拍摄到的第一人脸图像与目标人脸图像的目标相似度时，可以将目标相似度与确定出的当前场景对应的相似度阈值进行比较，如果目标相似度达到当前场景对应的相似度阈值，则发出第一人脸图像对应的预警信息，其中，拍摄的人脸图像不清晰时，往往计算出的各拍摄到的人脸图像与目标人脸图像的相似度的波动性程度值较大，这种情况下，可以通过提高相似度阈值，得到与当前场景相适应的相似度阈值。这样，终端每次得到目标 相似度时，是将其与当前场景相适应的相似度阈值进行比较，不是与预设相似度阈值进行比较，进而，可以减小由于误判发出的预警信息的数量，从而，可以提高预警的精确度。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。在附图中：
图1是根据一示例性实施例示出的一种发出预警信息的方法流程图；
图2是根据一示例性实施例示出的一种系统框架示意图；
图3是根据一示例性实施例示出的一种发出预警信息的装置的示意图；
图4是根据一示例性实施例示出的一种终端的结构示意图；
图5是根据一示例性实施例示出的一种发出预警信息的系统的示意图。
通过上述附图，已示出本公开明确的实施例，后文中将有更详细的描述。这些附图和文字描述并不是为了通过任何方式限制本公开构思的范围，而是通过参考特定实施例为本领域技术人员说明本公开的概念。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
本公开一示例性实施例提供了一种发出预警信息的方法，该方法可以用于终端中，其中，终端可以是个人电脑，该终端可以与前端设备(拍摄装置)进行数据通信。该终端中可以设置有处理器、存储器和收发器，处理器可以用于得到预警信息的相关处理，存储器可以用于存储下述处理过程中需要和产生的数据，收发器可以用于接收和发送数据。还可以设置有显示器，显示器可以用于显示预警信息。
下面将结合实施方式，对图1所示的处理流程进行详细的说明，内容可以 如下：
在步骤101中，获取已生成的预警信息对应的相似度。
在一个可选实施例中，终端可以具有人脸预警功能，并且可以预先存储有初始相似度阈值。为了确定目标人物所在的位置，在人脸预警功能开启的状态下，终端可以实时获取与其进行数据通信的拍摄装置拍摄到的人脸图像。对于每个获取到的人脸图像，终端可以根据预设的人脸识别算法，计算该人脸图像与预先存储的目标人物的目标人脸图像的相似度，进而，可以判断得到的相似度与初始相似度阈值的大小关系，如果计算出的相似度大于或等于初始相似度阈值，则终端可以生成并发出该人脸图像对应的预警信息，其中，人脸图像对应的预警信息可以包括人脸图像、相似度、目标人脸图像，还可以包括拍摄该人脸图像的拍摄装置所在的位置。也就是说，在初始阶段，每当计算出相似度后，可以将其与初始相似度阈值进行比较。
目标人脸图像可以是服务器或者是终端或者是拍摄装置中存储的人脸图像，例如，注册用户的孩子的脸部照片、走失老人的证件照等等。
在终端的工作过程中，终端可以根据场景变化，自适应调整当前场景对应的相似度阈值。具体的，终端中可以设置有相似度阈值的计算触发事件，在人脸预警功能开启的状态下，每当检测到相似度阈值的计算触发事件发生时，可以获取已生成的预警信息对应的相似度。
可选的，基于相似度阈值的计算触发事件不同，步骤101的处理方式可以多种多样，以下给出了几种可行的处理方式：
方式一，每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
在一个可选实施例中，终端中可以预先设置有获取周期，即可以将预设的获取周期作为相似度阈值的计算触发事件。也就是说，在人脸预警功能开启的状态下，每经过预设的获取周期，终端即可以获取上一获取周期内已生成的预警信息对应的相似度。例如，终端接收到人脸预警功能开启指令的时刻为9:00，周期为一小时，则到达10:00时，终端可以获取9:00到10:00之间生成的预警信息对应的相似度，到达11:00时，终端可以获取10:00到11:00之间生成的预警信息对应的相似度，以此类推。
方式二，每当已生成的预警信息的数量达到第二预设数量阈值时，获取已生成的预警信息对应的相似度。
在一个可选实施例中，终端中可以预先存储有数量阈值(即第二预设数量阈值)。此种情况下，每当已生成的预警信息的数量达到第二预设数量阈值时，终端可以获取此次已生成的预警信息对应的相似度。例如，第二预设数量阈值为20，终端接收到人脸预警功能开启指令后，生成的预警信息的数量达到20时，终端即可获取已生成的20个预警信息对应的相似度，此时，可以重新对生成的预警信息的数量进行计数，当后续生成的预警信息的数量再次达到20时，终端可以再获取此次已生成的20个预警信息对应的相似度。
方式三：每当计算出相似度阈值时，开始计时，并对已生成的预警信息的数量开始计数；当计时时长达到预设时长、或者计数数量达到第二预设数量阈值时，获取已生成的预警信息对应的相似度。
在一个可选的实施例中，每当计算出相似度阈值时，可以重新开始计时，并对已生成的预警信息的数量重新开始计数，其中，计算相似度阈值的具体处理过程将在后续进行详细的表述。当计时时长达到预设时长、或者计数数量达到第二预设数量阈值时，获取已生成的预警信息对应的相似度，也就是说，上述条件中只要满足其一，终端就可获取已生成的预警信息对应的相似度。
在步骤102中，根据已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值。
在一个可选实施例中，获取到已生成的预警信息对应的相似度后，终端可以确定已生成的预警信息对应的相似度的波动性程度值，进而，可以基于确定出的波动性程度值的大小，对相似度阈值的大小进行调整，将调整后的相似度阈值确定为当前场景对应的相似度阈值。
可选的，确定相似度阈值的具体处理过程可以如下：计算已生成的预警信息对应的相似度的波动性程度值；如果波动性程度值大于第一预设波动阈值，则将已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
在一个可选实施例中，获取到已生成的预警信息对应的相似度后，终端可以根据预设的波动性程度值的计算公式，计算相似度的波动性程度值，其中，波动性程度值可以是已生成的预警信息对应的相似度的方差或者标准差。例如，获取到的4个已生成的预警信息对应的相似度为a、b、c、d，则终端可以按照方差或者标准差的计算公式，计算a、b、c、d的方差或标准差。得到波动性程度值后，终端可以将其与第一预设波动阈值进行比较，如果获取到的相 似度的波动性程度值大于第一预设波动阈值(此种情况说明，当前场景中拍摄到的人脸图像的清晰度较低，导致拍摄到的人脸图像是非目标人物时，可能将其误判为目标人物)，则终端可以计算已生成的预警信息对应的相似度的平均值，进而，可以将计算出的平均值确定为当前场景对应的相似度阈值。也就是说，已生成的预警信息对应的相似度的波动性程度值较大时，可以适当的提高当前场景对应的相似度阈值，以便终端后续生成的预警信息的数量降低，进而，可以减轻工作人员对预警信息进行人工确认的压力。例如，之前的相似度阈值为70，已获取到的预警信息对应的相似度分别为71、75、80、78，则终端可以将71、75、80、78的平均值76，确定为当前场景对应的相似度阈值。
可选的，终端还可以在相似度阈值较高时，适当的降低后续使用的相似度阈值，相应的，处理过程可以如下：如果波动性程度值小于第二预设波动阈值，且已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
在一个可选实施例中，得到波动性程度值后，终端还可以将波动性程度值与第二预设波动阈值进行比较，如果波动性程度值小于第二预设波动阈值，则终端可以进一步比较获取到的已生成的预警信息的数量和第一预设数量阈值的大小，如果已生成的预警信息的数量小于第一预设数量阈值，则终端可以在原来的相似度阈值的基础上适当的降低相似度阈值。
可选地，如果波动性程度值小于第二预设波动阈值，且已生成的预警信息的数量小于第一预设数量阈值，则终端可以在确定此次下调的下调数值后，将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值，其中，下调数值可以是预设数值，也可以是根据上次确定出的相似度阈值确定出来的。对于后者，终端可以将相似度的上限值与上次确定出的相似度阈值的差值的一半，确定为下调数值，例如，上一次确定出的相似度阈值为80，上限值为100，则终端可以将100与80的差值的一半(即为10)确定为下调数值。这样，生成的预警信息的数量较少时，可以适当的降低相似度阈值，以便终端可以生成适量的预警信息，并且增大查找到目标人物的可能。
可选的，终端还可以在相似度阈值位于预设范围内时，不对上次确定出的相似度阈值进行改变，相应的，处理过程可以如下：如果波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的 相似度阈值，确定为当前场景对应的相似度阈值。
在一个可选实施例中，将计算出的相似度阈值与第一预设波动阈值和第二预设波动阈值进行比较后，如果波动性程度值介于第二预设波动阈值和第一预设波动阈值之间，则终端可以获取上次确定出的相似度阈值，并可以将其确定为当前场景对应的相似度阈值，即此种情况下，可以不对上次确定出的相似度阈值进行改变，可以在后续过程中继续使用。
在步骤103中，每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算第一人脸图像与预先存储的目标人脸图像的目标相似度。
在一个可选实施例中，终端可以与前端设备(拍摄装置)进行数据通信，每当拍摄装置拍摄到人脸图像(可以称为第一人脸图像)时，可以将其发送至终端，如图2所示。终端接收到第一人脸图像后，可以根据预设的人脸识别算法，计算第一人脸图像与预先存储的目标人脸图像的相似度(即目标相似度)，其中，目标人脸图像可以是目标人物的人脸图像。
另外，终端每当确定出当前场景对应的相似度阈值后，可以将其发送至拍摄装置，相应的，拍摄装置接收到当前场景对应的相似度阈值后，可以进行存储，并每当拍摄到第一人脸图像时，可以将第一人脸图像和接收到的相似度阈值，按照预设格式，生成任务数据。例如，可以按照表格的形式，生成包含第一人脸图和相似度阈值的任务数据，任务数据还可以包括拍摄装置所在的位置和标识等信息。生成任务数据后，可以将任务数据发送至终端，相应的，终端接收到任务数据后，可以获取其中的第一人脸图像，并计算第一人脸图像与预先存储的目标人脸图像的目标相似度。
在步骤104中，如果目标相似度达到确定出的当前场景对应的相似度阈值，则发出第一人脸图像对应的预警信息。
在一个可选实施例中，计算出目标相似度后，终端将目标相似度与确定出的当前场景对应的相似度阈值的大小进行比较，如果目标相似度达到确定出的当前场景对应的相似度阈值，则终端可以生成并发出第一人脸图像对应的预警信息，其中，终端可以显示第一人脸图像对应的预警信息，或者，终端在显示第一人脸图像对应的预警信息的同时，发出报警声。
当终端与多个地点的拍摄装置进行通信时，即当终端可以获取到多个地点的拍摄装置拍摄的人脸图像时，终端可以分别确定每个地点对应的后续使用的 相似度阈值，即对于每个地点，终端均可按照上述步骤101-104所述的方法进行处理。具体的，对于每个地点，获取已生成的预警信息对应的相似度；根据已生成的预警信息对应的相似度的波动性程度值，确定该地点的当前场景对应的相似度阈值；每当获取到该地点的拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算第一人脸图像与预先存储的目标人脸图像的目标相似度；如果目标相似度达到该地点的当前场景对应的相似度阈值，则发出第一人脸图像对应的预警信息。
可选的，终端还可以将已生成的预警信息进行删除，相应的，处理过程可以如下：当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；将确定出的目标预警信息删除。
在一个可选实施例中，终端中还可以预先设置有对已生成的预警信息的删除机制。具体的，终端中可以预先设置有预警信息删除触发事件，每当检测到预警信息删除触发事件发生时，终端可以在当前存储的预警信息中，确定此次待删除的预警信息(可称为目标预警信息)。确定出目标预警信息后，终端可以将其从终端中删除，以便终端可以具有充足的存储空间存储后续生成的预警信息。
可选的，基于确定目标预警信息的方式不同，上述确定目标预警信息的方式可以多种多样，以下给出了几种可行的处理方式：
方式一，当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息。
在一个可选实施例中，终端每当生成预警信息时，可以相应的记录每个预警信息对应的生成时刻。另外，终端中可以预先设置有删除时刻，当检测到当前时刻即为预设删除时刻时，终端可以在当前存储的所有预警信息中，确定每个预警信息对应的生成时刻距离当前时刻的时长，进而，可以将获得的每个时长与预设时长阈值进行比较，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息。
方式二，当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
在一个可选实施例中，终端每当生成预警信息时，可以相应的记录每个预警信息对应的生成时刻。另外，终端中可以预先设置有删除时刻，当检测到当前时刻即为预设删除时刻时，终端可以在当前存储的所有预警信息中，确定每 个预警信息对应的生成时刻距离当前时刻的时长，进而，可以按照对应的时长由大到小的顺序，对各个预警信息进行排序。得到排序后的预警信息后，可以由前到后，选取预设数量个预警信息，进而，可以将选取出的预设数量个预警信息，确定为待删除的目标预警信息。
本公开实施例中，终端可以获取历史已经生成的预警信息对应的相似度，并根据预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值，进而，当计算出拍摄装置拍摄到的第一人脸图像与目标人脸图像的目标相似度时，可以将目标相似度与确定出的当前场景对应的相似度阈值进行比较，如果目标相似度达到当前场景对应的相似度阈值，则发出第一人脸图像对应的预警信息。拍摄的人脸图像不清晰时，往往计算出的各拍摄到的人脸图像与目标人脸图像的相似度的波动性程度值较大，这种情况下，可以通过提高相似度阈值，得到与当前场景相适应的相似度阈值。这样，终端每次得到目标相似度时，是将其与当前场景相适应的相似度阈值进行比较，不是与预设相似度阈值进行比较，进而，可以减小由于误判发出的预警信息的数量，从而，可以提高预警的精确度。
本公开又一示例性实施例提供了一种发出预警信息的装置，如图3所示，该装置包括：
获取模块310，用于获取已生成的预警信息对应的相似度；
确定模块320，用于根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值；
计算模块330，用于每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；
发出模块340，用于如果所述目标相似度达到确定出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。
可选的，所述确定模块320，用于：
计算所述已生成的预警信息对应的相似度的波动性程度值；
如果所述波动性程度值大于第一预设波动阈值，则将所述已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
可选的，所述确定模块320，还用于：
如果所述波动性程度值小于第二预设波动阈值，且所述已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
可选的，所述确定模块320，还用于：
如果所述波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的相似度阈值，确定为当前场景对应的相似度阈值。
可选的，所述获取模块310，用于：
每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
可选的，所述获取模块310，用于：
每当已生成的预警信息的数量达到第二预设数量阈值时，获取所述已生成的预警信息对应的相似度。
可选的，所述确定模块320，还用于：
当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；
将确定出的所述目标预警信息删除。
可选的，所述确定模块320，用于：
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息；或者，
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
本公开实施例中，终端可以获取历史已经生成的预警信息对应的相似度，并根据预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值，进而，当计算出拍摄装置拍摄到的第一人脸图像与目标人脸图像的目标相似度时，可以将目标相似度与确定出的当前场景对应的相似度阈值进行比较，如果目标相似度达到当前场景对应的相似度阈值，则发出第一人脸图像对应的预警信息，其中，拍摄的人脸图像不清晰时，往往计算出的各拍摄到的人脸图像与目标人脸图像的相似度的波动性程度值较大，这种情况下，可以通过提高相似度阈值，得到与当前场景相适应的相似度阈值。这样，终端每次得到目标 相似度时，是将其与当前场景相适应的相似度阈值进行比较，不是与预设相似度阈值进行比较，进而，可以减小由于误判发出的预警信息的数量，从而，可以提高预警的精确度。
需要说明的是：上述实施例提供的发出预警信息的装置在发出预警信息时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将终端的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的发出预警信息的装置与发出预警信息的方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
本公开再一示例性实施例示出了一种终端的结构示意图。参照图4，终端400可以包括以下一个或多个组件：处理组件402，存储器404，电源组件406，多媒体组件408，音频组件410，输入/输出(I/O)的接口412，传感器组件414，以及通信组件416。
处理组件402通常控制终端400的整体操作，诸如与显示，数据通信，相机操作和记录操作相关联的操作。处理元件402可以包括一个或多个处理器420来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件402可以包括一个或多个模块，便于处理组件402和其他组件之间的交互。例如，处理部件402可以包括多媒体模块，以方便多媒体组件408和处理组件402之间的交互。
存储器404被配置为存储各种类型的数据以支持在终端400的操作。这些数据的示例包括用于在终端400上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器404可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电力组件406为终端400的各种组件提供电力。电力组件406可以包括电源管理系统，一个或多个电源，及其他与为音频输出设备400生成、管理和分配电力相关联的组件。
多媒体组件408包括在所述终端400和用户之间的提供一个输出接口的屏 幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件408包括一个前置摄像头和/或后置摄像头。当终端400处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件410被配置为输出和/或输入音频信号。例如，音频组件410包括一个麦克风(MIC)，当音频输出设备400处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器404或经由通信组件416发送。
I/O接口412为处理组件402和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件414包括一个或多个传感器，用于为终端400提供各个方面的状态评估。例如，传感器组件414可以检测到终端400的打开/关闭状态，组件的相对定位，例如所述组件为终端400的显示器和小键盘，传感器组件414还可以检测终端400或终端400一个组件的位置改变，用户与终端400接触的存在或不存在，终端400方位或加速/减速和终端400的温度变化。传感器组件414可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件414还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件414还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件416被配置为便于终端400和其他设备之间有线或无线方式的通信。终端400可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信部件416经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信部件416还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB) 技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，终端400可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器404，上述指令可由终端400的处理器420执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
一种非临时性计算机可读存储介质，所述存储介质中的指令被处理器执行时，以实现发出预警信息的方法，该方法包括：
获取已生成的预警信息对应的相似度；
根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值；
每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；
如果所述目标相似度达到确定出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
计算所述已生成的预警信息对应的相似度的波动性程度值；
如果所述波动性程度值大于第一预设波动阈值，则将所述已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
如果所述波动性程度值小于第二预设波动阈值，且所述已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
如果所述波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的相似度阈值，确定为当前场景对应的相似度阈值。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
每当已生成的预警信息的数量达到第二预设数量阈值时，获取所述已生成的预警信息对应的相似度。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；
将确定出的所述目标预警信息删除。
可选的，所述存储介质中的指令还可以被处理器执行以实现：
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息；或者，
当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
如图5所示，本公开提供一种发出预警信息的系统500，包括：上述实施例提供的发出预警信息的装置501，以及拍摄装置502。
本公开实施例中，终端可以获取历史已经生成的预警信息对应的相似度，并根据预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值，进而，当计算出拍摄装置拍摄到的第一人脸图像与目标人脸图像的目标相似度时，可以将目标相似度与确定出的当前场景对应的相似度阈值进行比较，如果目标相似度达到当前场景对应的相似度阈值，则发出第一人脸图像对应的预警信息，其中，拍摄的人脸图像不清晰时，往往计算出的各拍摄到的人脸图像与目标人脸图像的相似度的波动性程度值较大，这种情况下，可以通过提高相似度阈值，得到与当前场景相适应的相似度阈值。这样，终端每次得到目标相似度时，是将其与当前场景相适应的相似度阈值进行比较，不是与预设相似度阈值进行比较，进而，可以减小由于误判发出的预警信息的数量，从而，可以提高预警的精确度。
本领域技术人员在考虑说明书及实践这里公开的公开后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性 的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (19)

  1. 一种发出预警信息的方法，其特征在于，所述方法包括：
    获取已生成的预警信息对应的相似度；
    根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值；
    每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；
    如果所述目标相似度达到确定出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值，包括：
    计算所述已生成的预警信息对应的相似度的波动性程度值；
    如果所述波动性程度值大于第一预设波动阈值，则将所述已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
  3. 根据权利要求2所述的方法，其特征在于，所述方法还包括：
    如果所述波动性程度值小于第二预设波动阈值，且所述已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
  4. 根据权利要求2或3所述的方法，其特征在于，所述方法还包括：
    如果所述波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的相似度阈值，确定为当前场景对应的相似度阈值。
  5. 根据权利要求1所述的方法，其特征在于，所述获取已生成的预警信息对应的相似度，包括：
    每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
  6. 根据权利要求1所述的方法，其特征在于，所述获取已生成的预警信息对应的相似度，包括：
    每当已生成的预警信息的数量达到第二预设数量阈值时，获取所述已生成的预警信息对应的相似度。
  7. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；
    将确定出的所述目标预警信息删除。
  8. 根据权利要求7所述的方法，其特征在于，所述当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息，包括：
    当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息；或者，
    当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
  9. 一种发出预警信息的装置，其特征在于，所述装置包括：
    获取模块，用于获取已生成的预警信息对应的相似度；
    确定模块，用于根据所述已生成的预警信息对应的相似度的波动性程度值，确定当前场景对应的相似度阈值；
    计算模块，用于每当获取到拍摄装置拍摄到的第一人脸图像时，根据预设的人脸识别算法，计算所述第一人脸图像与预先存储的目标人脸图像的目标相似度；
    发出模块，用于如果所述目标相似度达到确定出的当前场景对应的相似度阈值，则发出所述第一人脸图像对应的预警信息。
  10. 根据权利要求9所述的装置，其特征在于，所述确定模块，用于：
    计算所述已生成的预警信息对应的相似度的波动性程度值；
    如果所述波动性程度值大于第一预设波动阈值，则将所述已生成的预警信息对应的相似度的平均值，确定为当前场景对应的相似度阈值。
  11. 根据权利要求10所述的装置，其特征在于，所述确定模块，还用于：
    如果所述波动性程度值小于第二预设波动阈值，且所述已生成的预警信息的数量小于第一预设数量阈值，则确定下调数值，并将上次确定出的相似度阈值与下调数值的差值，确定为当前场景对应的相似度阈值。
  12. 根据权利要求10或11所述的装置，其特征在于，所述确定模块，还用于：
    如果所述波动性程度值小于或等于第一预设波动阈值，且大于或等于第二预设波动阈值，则将上次确定出的相似度阈值，确定为当前场景对应的相似度 阈值。
  13. 根据权利要求9所述的装置，其特征在于，所述获取模块，用于：
    每经过预设的获取周期，获取上一获取周期内已生成的预警信息对应的相似度。
  14. 根据权利要求9所述的装置，其特征在于，所述获取模块，用于：
    每当已生成的预警信息的数量达到第二预设数量阈值时，获取所述已生成的预警信息对应的相似度。
  15. 根据权利要求9所述的装置，其特征在于，所述确定模块，还用于：
    当检测到预警信息删除触发事件发生时，确定待删除的目标预警信息；
    将确定出的所述目标预警信息删除。
  16. 根据权利要求15所述的装置，其特征在于，所述确定模块，用于：
    当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长大于预设时长阈值的预警信息，确定为待删除的目标预警信息；或者，
    当检测到当前时刻为预设删除时刻时，将对应的生成时刻距离当前时刻的时长最大的预设数量个预警信息，确定为待删除的目标预警信息。
  17. 一种计算机可读存储介质，其特征在于，所述存储介质内存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1-8任一所述的方法步骤。
  18. 一种发出预警信息的系统，其特征在于，所述系统包括：如权利要求9-16中任一项所述的装置，以及拍摄装置。
  19. 一种终端，其特征在于，所述终端包括：
    一个或多个处理器；和
    存储器；
    所述存储器存储有一个或多个程序，所述一个或多个程序被配置成由所述一个或多个处理器执行，所述一个或多个程序包含用于进行如权利要求1-8任一所述的方法步骤的指令。
PCT/CN2018/091028 2017-06-15 2018-06-13 一种发出预警信息的方法、装置及系统 WO2018228422A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US16/622,864 US11361586B2 (en) 2017-06-15 2018-06-13 Method for sending warning information, storage medium and terminal
EP18817320.7A EP3640838A4 (en) 2017-06-15 2018-06-13 METHOD, DEVICE AND SYSTEM FOR TRANSMITTING WARNING INFORMATION

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710454708.8 2017-06-15
CN201710454708.8A CN109145679B (zh) 2017-06-15 2017-06-15 一种发出预警信息的方法、装置及系统

Publications (1)

Publication Number Publication Date
WO2018228422A1 true WO2018228422A1 (zh) 2018-12-20

Family

ID=64658913

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/091028 WO2018228422A1 (zh) 2017-06-15 2018-06-13 一种发出预警信息的方法、装置及系统

Country Status (4)

Country Link
US (1) US11361586B2 (zh)
EP (1) EP3640838A4 (zh)
CN (1) CN109145679B (zh)
WO (1) WO2018228422A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116894102A (zh) * 2023-06-26 2023-10-17 珠海微度芯创科技有限责任公司 毫米波成像视频流的过滤方法、装置、设备、存储介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111556312B (zh) * 2020-04-27 2021-11-02 峰米(北京)科技有限公司 一种视频卡顿的检测方法、装置、系统和存储介质
CN112199998B (zh) * 2020-09-09 2023-06-20 浙江大华技术股份有限公司 一种人脸识别方法、装置、设备及介质
CN112685277B (zh) * 2020-12-31 2023-01-24 海光信息技术股份有限公司 警告信息检查方法、装置、电子设备和可读存储介质
CN113326173B (zh) * 2021-08-04 2021-11-23 云智慧（北京）科技有限公司 一种告警消息的处理方法、装置及设备
CN113762106A (zh) * 2021-08-23 2021-12-07 深圳云天励飞技术股份有限公司 人脸识别方法、装置、电子设备及存储介质
CN114116849A (zh) * 2021-12-01 2022-03-01 南威软件股份有限公司 一种针对人像预警信息的二次研判方法及装置
CN115034810A (zh) * 2022-05-18 2022-09-09 北京羽乐创新科技有限公司 数据分析方法及装置
CN115512499A (zh) * 2022-08-12 2022-12-23 四川弘和通讯集团有限公司 一种加油站自动干预方法、系统、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103037157A (zh) * 2011-09-28 2013-04-10 卡西欧计算机株式会社 图像处理装置以及图像处理方法
CN103093209A (zh) * 2013-01-23 2013-05-08 深圳市亚略特生物识别科技有限公司 指纹验证系统
CN105468955A (zh) * 2015-12-28 2016-04-06 深圳市亚略特生物识别科技有限公司 基于生物识别的移动终端及电子系统
CN106022032A (zh) * 2015-03-30 2016-10-12 欧姆龙株式会社 个人识别装置、识别阈值设定方法、以及程序

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI278782B (en) * 2001-08-24 2007-04-11 Toshiba Corp Personal recognition apparatus
JP5010905B2 (ja) * 2006-12-13 2012-08-29 パナソニック株式会社 顔認証装置
CA2804468C (en) * 2012-01-30 2016-03-29 Accenture Global Services Limited System and method for face capture and matching
CN102622579B (zh) 2012-02-20 2014-03-19 华焦宝 人脸预警方法及系统
JP5992276B2 (ja) * 2012-09-20 2016-09-14 株式会社東芝 人物認識装置、及び方法
CN105488478B (zh) 2015-12-02 2020-04-07 深圳市商汤科技有限公司 一种人脸识别系统和方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103037157A (zh) * 2011-09-28 2013-04-10 卡西欧计算机株式会社 图像处理装置以及图像处理方法
CN103093209A (zh) * 2013-01-23 2013-05-08 深圳市亚略特生物识别科技有限公司 指纹验证系统
CN106022032A (zh) * 2015-03-30 2016-10-12 欧姆龙株式会社 个人识别装置、识别阈值设定方法、以及程序
CN105468955A (zh) * 2015-12-28 2016-04-06 深圳市亚略特生物识别科技有限公司 基于生物识别的移动终端及电子系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3640838A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116894102A (zh) * 2023-06-26 2023-10-17 珠海微度芯创科技有限责任公司 毫米波成像视频流的过滤方法、装置、设备、存储介质
CN116894102B (zh) * 2023-06-26 2024-02-20 珠海微度芯创科技有限责任公司 毫米波成像视频流的过滤方法、装置、设备、存储介质

Also Published As

Publication number Publication date
US11361586B2 (en) 2022-06-14
EP3640838A1 (en) 2020-04-22
US20200201688A1 (en) 2020-06-25
CN109145679B (zh) 2020-05-12
EP3640838A4 (en) 2020-06-03
CN109145679A (zh) 2019-01-04

Similar Documents

Publication Publication Date Title
WO2018228422A1 (zh) 一种发出预警信息的方法、装置及系统
US10013600B2 (en) Digital image processing method and apparatus, and storage medium
US10115019B2 (en) Video categorization method and apparatus, and storage medium
RU2597232C1 (ru) Способ предоставления видео в режиме реального времени и устройство для его осуществления, а также сервер и терминальное устройство
WO2017020408A1 (zh) 视频录制方法和装置
US20170178289A1 (en) Method, device and computer-readable storage medium for video display
US10292004B2 (en) Method, device and medium for acquiring location information
WO2017071085A1 (zh) 报警方法及装置
WO2016029641A1 (zh) 照片获取方法及装置
WO2017088470A1 (zh) 图像分类方法及装置
US20170154206A1 (en) Image processing method and apparatus
WO2017096782A1 (zh) 防止拍照遮挡的方法及装置
WO2017071088A1 (zh) 图像获取方法及装置
WO2015184723A1 (zh) 拍摄控制方法、装置及终端
WO2016155232A1 (zh) 号码标记方法及装置
WO2017020476A1 (zh) 关联用户的确定方法及装置
WO2019006769A1 (zh) 无人机跟拍方法及装置
WO2017000491A1 (zh) 获取虹膜图像的方法、装置及红膜识别设备
WO2017197778A1 (zh) 图像发送方法和装置
CN106534951B (zh) 视频分割方法和装置
US20170090684A1 (en) Method and apparatus for processing information
WO2016026293A1 (zh) 消息发送方法及装置
CN107734303B (zh) 视频标识方法及装置
CN108986803B (zh) 场景控制方法及装置、电子设备、可读存储介质
CN111832455A (zh) 获取内容图像的方法、装置、存储介质和电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18817320

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018817320

Country of ref document: EP

Effective date: 20200115